66 lines
2.0 KiB
Python
66 lines
2.0 KiB
Python
|
#!/usr/bin/env python
|
|||
|
|
# -*- coding: utf-8 -*-
|
|||
|
|
"""
|
|||
|
|
使用XPath语法统计HTML文件中"视频上传成功"文本的出现次数
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
from lxml import etree
|
|||
|
|
import html
|
|||
|
|
|
|||
|
|
def count_text_with_xpath(html_file, search_text):
|
|||
|
|
"""
|
|||
|
|
使用XPath查找指定文本在HTML中的出现次数
|
|||
|
|
|
|||
|
|
Args:
|
|||
|
|
html_file: HTML文件路径
|
|||
|
|
search_text: 要搜索的文本
|
|||
|
|
|
|||
|
|
Returns:
|
|||
|
|
出现次数
|
|||
|
|
"""
|
|||
|
|
# 读取HTML文件
|
|||
|
|
with open(html_file, 'r', encoding='utf-8') as f:
|
|||
|
|
html_content = f.read()
|
|||
|
|
|
|||
|
|
# 解析HTML
|
|||
|
|
parser = etree.HTMLParser()
|
|||
|
|
tree = etree.fromstring(html_content.encode('utf-8'), parser)
|
|||
|
|
|
|||
|
|
# XPath表达式：查找包含指定文本的所有节点
|
|||
|
|
# 使用contains()函数来匹配包含指定文本的节点
|
|||
|
|
xpath_expr = f"//text()[contains(., '{search_text}')]"
|
|||
|
|
|
|||
|
|
# 执行XPath查询
|
|||
|
|
results = tree.xpath(xpath_expr)
|
|||
|
|
|
|||
|
|
# 统计出现次数（可能一个文本节点包含多次出现）
|
|||
|
|
total_count = 0
|
|||
|
|
for text_node in results:
|
|||
|
|
# 计算该文本节点中搜索文本的出现次数
|
|||
|
|
count = text_node.count(search_text)
|
|||
|
|
total_count += count
|
|||
|
|
print(f"找到文本节点，内容片段: ...{text_node[:100]}... (包含 {count} 次)")
|
|||
|
|
|
|||
|
|
return total_count, len(results)
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
html_file = "1.html"
|
|||
|
|
search_text = "视频上传成功"
|
|||
|
|
|
|||
|
|
print(f"正在使用XPath查找文本: '{search_text}'")
|
|||
|
|
print("=" * 60)
|
|||
|
|
|
|||
|
|
total_count, node_count = count_text_with_xpath(html_file, search_text)
|
|||
|
|
|
|||
|
|
print("=" * 60)
|
|||
|
|
print(f"XPath查询结果:")
|
|||
|
|
print(f" - 包含该文本的文本节点数量: {node_count}")
|
|||
|
|
print(f" - 文本总出现次数: {total_count}")
|
|||
|
|
|
|||
|
|
# 也提供其他XPath表达式示例
|
|||
|
|
print("\n" + "=" * 60)
|
|||
|
|
print("其他可用的XPath表达式示例:")
|
|||
|
|
print(f" 1. //text()[contains(., '{search_text}')]")
|
|||
|
|
print(f" 2. //*[contains(text(), '{search_text}')]")
|
|||
|
|
print(f" 3. //*[normalize-space(text())='{search_text}']")
|